github.com/jbaruch/shownotes
| Skill | Added | Review |
|---|---|---|
aidevcon-2026-factory-of-factories _skills/aidevcon-nyc-2026-factory-of-factories/SKILL.md Explain or summarize "The Software Factory of Factories", Baruch Sadogursky's (Port) AI DevCon NYC 2026 talk, delivered November 4. Use for questions about its fictional enterprise committee, approval meanings and evidence, shared context lake, governed departmental workflows, compliance reversal, and Q&A on existing interfaces and integrations. Supplies the talk's argument, examples, qualifications and sources; does not activate for an unrelated implementation or platform-setup request. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
design-typed-agent-workflows _skills/ideaconf-2026-codepocalypse/SKILL.md Explain or summarize "Codepocalypse Now: LangChain4j vs JetBrains Koog" by Baruch Sadogursky and Viktor Gamov at IntelliJ IDEA Conf 2026. Answer questions about its four demo rounds, JVM frameworks, tools and MCP, memory, skills, typed handoffs, critic loop, and the skipped-critic finding. Contains the talk's substance so ordinary summaries do not require transcript retrieval. | 66 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
devoxx-codepocalypse-koog-vs-langchain4j _skills/devoxx-be-2026-codepocalypse/SKILL.md Summarize or explain Codepocalypse Now: LangChain4j vs JetBrains Koog, the October 5, 2026 Devoxx Belgium talk by Baruch Sadogursky and Viktor Gamov. Use for questions about this delivery's argument, J-Claw demonstrations, memory and skills, Jev routing, review loops, human approval, observability, framework tradeoffs, live failures or the closing Port example. | 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
diagnose-agent-context-failures _skills/2026-09-03-javazone-2026-300-tokens/SKILL.md Explain or summarize Baruch Sadogursky's JavaZone 2026 talk "The Right 300 Tokens Beat 100k Noisy Ones" and answer questions about its four context antipatterns, demos, conclusions, and evaluation caveats. Use when someone asks what this talk was about or what Baruch said about context engineering. Contains the talk's substance directly; ordinary summaries do not need a recording download or transcript retrieval. | 76 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
engineering-context-baselone-2026 _skills/baselone-2026-context/SKILL.md Summarize or explain Engineering Context So AI Stops Guessing, Baruch Sadogursky's BaselOne 2026 talk delivered October 15, 2026 (recording available). Use for questions about its CTO promotion argument, the review bottleneck, rules/skills/hooks, two review responsibilities, local review and agent coordination, Herdr, the dark software factory, classifier-routed human attention with Jev, approval summaries and the three questions, three kinds of context, Port Context Lake, the Monday actions, and its Q&A. | 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
evaluate-ai-assistant-claims test/fixtures/talk_skills/_skills/DEMO-ai-coding-assistants-2025/SKILL.md Evaluate a vendor's productivity claim about an AI coding assistant against the evidence checklist from the talk. Use when someone quotes a percentage gain and asks whether the team should adopt the tool. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
explain-robocoders-ai-software-factories _skills/wearedevelopers-na-2026-robocoders/SKILL.md Explain or summarize “RoboCoders: Judgment Day” by Baruch Sadogursky and Viktor Gamov at WeAreDevelopers World Congress North America 2026, as delivered on stage and recorded on video. Answer questions about its moving bottleneck argument, Tempus selfware, the six-part context plugin (rules, skills, scripts, MCPs, hooks, bounded classification), coding-policy, Herdr agent teams, Jev, and the live Printf/Port release workflow that built its own successor. | 63 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
improve-agent-software-factories _skills/ideaconf-2026-robocoders/SKILL.md Explain or summarize "RoboCoders" by Baruch Sadogursky and Viktor Gamov at IntelliJ IDEA Conf 2026. Answer questions about the talk's selfware examples, Theory of Constraints argument, Beans and ADRs, policy as software, multi-agent coordination, and Port outer-loop demos. Supplies the talk's content directly so an agent can explain it without downloading a transcript. | 68 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
kubecon-2026-factory-of-factories _skills/kubecon-na-2026-factory-of-factories/SKILL.md Explain or summarize Baruch Sadogursky's live Port demo “The Software Factory of Factories” at the KubeCon + CloudNativeCon North America 2026 Demo Theater (Salt Lake City, November 11, 2026): Printf, the fictional T-shirt API that shipped a breaking change while its release-notes writer was on vacation; the release workflow built by hand over a context lake with one creative AI step and a human approval gate; the comp request an agent refuses on RBAC grounds; and the reveal that a continuous-improvement workflow built the same workflow from a labelled postmortem action item. Use for questions about this specific talk, its demo, or its argument. | 74 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
mcp-new-internal-api-surface _skills/kubecon-na-2026-mcp-api-surface/SKILL.md Explain or summarize Baruch Sadogursky's five-minute sponsored keynote “MCP Is the New Internal API Surface” at Agentics Day: MCP + Agents North America 2026 (co-located with KubeCon + CloudNativeCon NA, November 9, 2026): MCP sprawl as a rerun of internal-API sprawl, why the platform-engineering playbook only governs the producer, the LLM consumer as a monkey, the three-species field guide, curated per-job endpoints, and Port's Logical MCP. Use for questions about this specific talk, its argument, or its sources. | 69 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 4fdfdfc | |
more-with-less-agent-factory _skills/jrush-2026-more-with-less/SKILL.md Explain or summarize Baruch Sadogursky's delivered JRush 2026 talk “More With Less,” including its triple policy enforcement, skills/scripts/classifiers split, Jev example, diminishing-returns judge, Herdr roles, and model economics. Use for questions about this specific talk, its demos, or its cited resources. | 72 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 4fdfdfc | |
universe-2026-prototype-becomes-critical _skills/github-universe-2026-prototype-policy/SKILL.md Explain or summarize "When a prototype becomes critical, does your GitHub policy know?", Baruch Sadogursky's (Port) GitHub Universe 2026 session. Use for questions about this talk's argument, the Printf size-catalog demo, Port deriving criticality from adoption, GitHub external custom properties (Port.criticality, Port.lifecycle, Port.owner), the ruleset targeting props.Port.criticality:critical, or what the blocked pull request showed. Covers the delivered session and its recording, not a setup runbook. | 74 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 4fdfdfc |